
# importing
import os
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns

color_pal = sns.color_palette()
plt.style.use('fivethirtyeight')


# Define the path of the input and output folders
input_folder = './running_data'
output_folder = './running_data_transformed'

print('PREPARING APPLE HEALTH CSV EXPORTS')
print(' ')

# Get a list of all CSV files in the input folder
csv_files = [f for f in os.listdir(input_folder) if f.endswith('.csv')]

# Loop through each CSV file
for file in csv_files:
    # Construct the full path of the input file
    input_file = os.path.join(input_folder, file)
    
    # Construct the full path of the output file
    output_file = os.path.join(output_folder, file)
    
    # Check if the output file already exists, and skip if it does
    if os.path.exists(output_file):
        print(f'{output_file} already exists, skipping...')
        continue
    
    # Read in the CSV file as a dataframe, with the first column as the index
    df = pd.read_csv(os.path.join(input_folder, file))
    df.rename(columns = lambda x: x.strip().lower().replace(" ", "_"), inplace=True)

    # Apply transformations
    # Remove hh-mm-ss

    # Apply transformations
    # Remove hh-mm-ss
    df['date'] = df['date'].apply(lambda x: x.split()[0])
    # Convert to datetime
    df['date'] = pd.to_datetime(df['date'])
    # Set as index
    df = df.set_index('date')  # Set the 'date' column as the index

    # Save the transformed dataframe as a new csv file
    new_file_name = os.path.splitext(file)[0] + '_transformed.csv'  # Create a new file name
    
    # Save the dataframe as a CSV file in the output folder
    df.to_csv(os.path.join(output_folder, new_file_name), index=True) 
    
    print(f'{input_file} processed and saved to {output_file}.')

print(' ')
print('LOADING PROCESSED APPLE HEALTH CSV EXPORTS AS DATAFRAMES')
print(' ')
# Get a list of all CSV files in the folder
transformed_csv_files = [f for f in os.listdir(output_folder) if f.endswith('.csv')]

# Loop through each transformed CSV file
for file in transformed_csv_files:
    # Construct the full path of the CSV file
    file_path = os.path.join(output_folder, file)
    
    # Read the CSV file into a dataframe
    df_name = os.path.splitext(file)[0].split('_')[0]  # use the filename as the dataframe name
    globals()[df_name] = pd.read_csv(file_path)
    
    # setting date column as index in all dataframes
    globals()[df_name]['date'] = pd.to_datetime(globals()[df_name]['date'])
    globals()[df_name].set_index(['date'], inplace=True)
    
    print(f'{file_path} loaded as {df_name}.')

PREPARING APPLE HEALTH CSV EXPORTS
 
./running_data/workouts.csv processed and saved to ./running_data_transformed/workouts.csv.
./running_data/insulin.csv processed and saved to ./running_data_transformed/insulin.csv.
./running_data/energy.csv processed and saved to ./running_data_transformed/energy.csv.
./running_data/glucose2.csv processed and saved to ./running_data_transformed/glucose2.csv.
./running_data/glucose.csv processed and saved to ./running_data_transformed/glucose.csv.
 
LOADING PROCESSED APPLE HEALTH CSV EXPORTS AS DATAFRAMES
 
./running_data_transformed/insulin_transformed.csv loaded as insulin.
./running_data_transformed/workouts_transformed.csv loaded as workouts.
./running_data_transformed/glucose_transformed.csv loaded as glucose.
./running_data_transformed/energy_transformed.csv loaded as energy.
./running_data_transformed/glucose2_transformed.csv loaded as glucose2.


insulin.tail()


workouts.tail()


energy.tail()


glucose.tail()


# Aggregate data for workouts in same day
glucose = glucose.groupby('date').agg({'blood_glucose(mg/dl)': 'mean', 
                                       'insulin_delivery(iu)': 'sum', 
                                               })
glucose.tail()
# insulin data is 0 in March due to device issues


# from seconds to minutes
workouts['duration(s)']=workouts['duration(s)'].apply(lambda x:x/60)
workouts.rename({'duration(s)':'duration(m)'}, axis=1, inplace=True)

# Look for the 'duration(m)' column
workouts.tail()


running = workouts.query("activity=='Running'")
running.tail()


running.columns

Index(['active_energy_burned(kcal)', 'activity', 'distance(km)', 'duration(m)',
       'elevation:_ascended(m)', 'elevation:_maximum(m)',
       'elevation:_minimum(m)', 'heart_rate_zone:_a_easy_(<115bpm)(%)',
       'heart_rate_zone:_b_fat_burn_(115-135bpm)(%)',
       'heart_rate_zone:_c_moderate_training_(135-155bpm)(%)',
       'heart_rate_zone:_d_hard_training_(155-175bpm)(%)',
       'heart_rate_zone:_e_extreme_training_(>175bpm)(%)',
       'heart_rate:_average(count/min)', 'heart_rate:_maximum(count/min)',
       'mets_average(kcal/hr·kg)', 'weather:_humidity(%)',
       'weather:_temperature(degc)'],
      dtype='object')


# renaming target columns
running = running.rename({'active_energy_burned(kcal)':'kcal_burned',
                'heart_rate_zone:_a_easy_(<115bpm)(%)':'zone1_(<115bpm)(%)',
                'heart_rate_zone:_b_fat_burn_(115-135bpm)(%)':'zone2_(115-135bpm)(%)',
                'heart_rate_zone:_c_moderate_training_(135-155bpm)(%)':'zone3_(135-155bpm)(%)',
                'heart_rate_zone:_d_hard_training_(155-175bpm)(%)':'zone4_(155-175bpm)(%)',
                'heart_rate_zone:_e_extreme_training_(>175bpm)(%)':'zone5_(>175bpm)(%)',
                'heart_rate:_average(count/min)':'avg_HR', 
                'heart_rate:_maximum(count/min)': 'max_HR'}, 
               axis=1, 
               #inplace=True # commenting it out to  avoid setting value on copy of slice od dataframe
              )
# removing extra columns
running = running.drop(['elevation:_ascended(m)', 
              'elevation:_maximum(m)',
              'elevation:_minimum(m)',
              'mets_average(kcal/hr·kg)', 
              'weather:_humidity(%)',
              'weather:_temperature(degc)'], 
                       axis=1,
                       #inplace=True # commenting it out to avoid setting value on copy of slice od dataframe
                      )


# Aggregate data for workouts in same day
running_grouped = running.groupby('date').agg({'kcal_burned': 'sum', # sum of calories, distance and duration
                                               'distance(km)': 'sum', 
                                               'duration(m)': 'sum',
                                               'zone1_(<115bpm)(%)': 'mean', # average of the other values
                                               'zone2_(115-135bpm)(%)': 'mean',
                                               'zone3_(135-155bpm)(%)': 'mean', 
                                               'zone4_(155-175bpm)(%)': 'mean',
                                               'zone5_(>175bpm)(%)': 'mean',
                                               'avg_HR':'mean',
                                               'max_HR':'mean'})
running_grouped.tail()


# saving the processed dataframe to the folder
running_grouped.to_csv(os.path.join(output_folder, 'running_transformed.csv'), index=True)


run = pd.read_csv(
    os.path.join(output_folder, 'running_transformed.csv'),
    parse_dates = ['date'],
    #infer_datetime_format=True,
    index_col = ['date']
)
run.head()


#import libraries
import plotly.express as px
import plotly.graph_objs as go
from plotly.subplots import make_subplots

# Define list of metrics to display in graphs
metrics = [
    'distance(km)', 
    'duration(m)',
    'kcal_burned'
]

# creating a dataframe for weekly data
df2 = run[metrics].copy()
df2.index = pd.to_datetime(df2.index)
weekly_df = (
    df2
    .resample('W')         # Referring to the Week 
    .sum()                 # Summing weekly data
    .round().astype(int))  # Making it more reader-friendly


# function that will generate a Plotly chart based on the user's selection
def generate_line_chart(metric):
    """
    This function takes a metric from the run dataset.
    It generates a Plotly bar chart with the date on the x-axis and the metric on the y-axis.
    """
    df=run.copy()
    fig = px.line(weekly_df, 
                  x=weekly_df.index, 
                  y=weekly_df[metric].rolling(14, 7).mean(),  # line with 14-day moving average
                  color_discrete_sequence=['#4169E1'],
                  #title="7 day moving average"
                 )
    fig.add_trace(go.Bar(x=weekly_df.index, 
                         y=weekly_df[metric],
                        name=metric),
                 )    
    
    # Annotating the peak
    peak_index = weekly_df[metric].idxmax()
    fig.add_annotation(x=peak_index, 
                       y=weekly_df.loc[peak_index, metric], 
                       text="Peak", 
                       showarrow=True, 
                       arrowhead=1)


    # Applying new theme and adding a title
    fig.update_layout(template='ggplot2',
                      title=f"Total weekly {metric.capitalize()} - Running", 
                      xaxis_title="Date", 
                      yaxis_title=metric,
                      showlegend=True,
                      shapes=[                     # Adding shape to highlight the Running School period
                          dict(
                                type='rect',
                                xref='x',
                                yref='paper',
                                x0='2023-01-21',
                                y0=0,
                                x1='2023-03-30',
                                y1=1,
                                fillcolor='blue',
                                opacity=0.2,
                                layer='below',
                                line_width=0
                            )
                      ])



    fig.show()
    
for metric in metrics:
    generate_line_chart(metric)


run.columns

Index(['kcal_burned', 'distance(km)', 'duration(m)', 'zone1_(<115bpm)(%)',
       'zone2_(115-135bpm)(%)', 'zone3_(135-155bpm)(%)',
       'zone4_(155-175bpm)(%)', 'zone5_(>175bpm)(%)', 'avg_HR', 'max_HR'],
      dtype='object')


# Subsetting dataframe
hrzones = run[['zone1_(<115bpm)(%)',
       'zone2_(115-135bpm)(%)', 'zone3_(135-155bpm)(%)',
       'zone4_(155-175bpm)(%)', 'zone5_(>175bpm)(%)']].loc[run.index>'2023-01-01'].mean()

avg_hr = pd.DataFrame(hrzones.reset_index())
avg_hr.columns = ['HR_Zone','avg_time_in_zone']
avg_hr['avg_time_in_zone(%)'] = round((avg_hr['avg_time_in_zone']*100).astype(int))
#avg_hr


# Subsetting dataframe
hrzones = run[['zone1_(<115bpm)(%)',
       'zone2_(115-135bpm)(%)', 'zone3_(135-155bpm)(%)',
       'zone4_(155-175bpm)(%)', 'zone5_(>175bpm)(%)']].loc[run.index>'2023-01-01'].mean()

avg_hr = pd.DataFrame(hrzones.reset_index())
avg_hr.columns = ['HR_Zone','avg_time_in_zone']
avg_hr['avg_time_in_zone(%)'] = round((avg_hr['avg_time_in_zone']*100).astype(int))
avg_hr = avg_hr.loc[~(avg_hr['avg_time_in_zone(%)']==0)]
#avg_hr


avg_hr = avg_hr.loc[~(avg_hr['avg_time_in_zone(%)']==0)]
avg_hr


#import libraries
import plotly.express as px
import plotly.graph_objs as go
from plotly.subplots import make_subplots

fig = px.treemap(avg_hr, 
                 path=['HR_Zone'], 
                 values='avg_time_in_zone(%)',
                 color='avg_time_in_zone(%)', 
                 color_continuous_scale='Blues'
                )

fig.update_layout(template='ggplot2',
                  title="Time in HR zones (%)",
                  #treemapcolorway = ["blue"],
                 )
fig.update_traces(#root_color="green",
                  marker=dict(cornerradius=5),
                  labels = ["Zone 1","Zone 2", "Zone 3", "Zone 4", "Zone 5"],
                  values = list(avg_hr['avg_time_in_zone(%)']),
                  textinfo = "label+value"
                 )
fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
fig.show()


import numpy as np
run['is_RS'] = np.where(run.index<'2023-01-21', 'N', 'Y')

# Subsetting dataframe
hrzones_RS = run[['zone1_(<115bpm)(%)',
       'zone2_(115-135bpm)(%)', 'zone3_(135-155bpm)(%)',
       'zone4_(155-175bpm)(%)', 'zone5_(>175bpm)(%)', 'is_RS']].loc[run['is_RS']=='Y'].mean()

/var/folders/0l/7mflm_6s5rb9r18y6bzvc_100000gn/T/ipykernel_42838/2654370482.py:7: FutureWarning:

Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.


import plotly.graph_objs as go
fig = go.Figure()

fig.add_trace(go.Scatter(
   x=run.loc[run['is_RS']=='N'].index,
   y=run.loc[run['is_RS']=='N']['avg_HR'],
    mode='lines',
   name="Before Running School")
)

fig.add_trace(go.Scatter(
   x=run.loc[run['is_RS']=='Y'].index,
   y=run.loc[run['is_RS']=='Y']['avg_HR'],
    mode='lines',
   name="During Running School")
)

# Annotating the peak
peak_index = run['avg_HR'].idxmax()
fig.add_annotation(x=peak_index, 
                   y=run.loc[peak_index, 'avg_HR'], 
                   text="Peak", 
                   showarrow=True, 
                   arrowhead=1)

# Before and After RS
fig.add_shape(type='line', x0='2023-01-21', y0=0, x1='2023-01-21', y1=max(run['max_HR'])-5,
              line=dict(color='black', width=3, dash='dash'))
# Add an annotation on the vertical line
fig.add_annotation(x='2023-01-21', y=max((run['max_HR'])), 
                   text='Start of Running School', 
                   showarrow=True, arrowhead=1
                  )


# Applying new theme and adding a title
fig.update_layout(template='ggplot2',
                  title=f"Average Heart Rate", 
                  xaxis_title="Date", 
                  yaxis_title='avg_HR'
                 )

fig.show()


# Summary of cardio activities over the last three months
cardio_activities = ['Walking', 'Running', 'Running (Indoor)', 'Cycling', 'Cycling (Indoor)']
cardio_df = workouts.loc[workouts["activity"].isin(cardio_activities)][['activity','active_energy_burned(kcal)','duration(m)' ]]
cardio_df = cardio_df.groupby('activity').sum().reset_index().sort_values(by=['duration(m)'], ascending=True)


cardio_df["%_of_total_time"]=(cardio_df['duration(m)'] / cardio_df['duration(m)'].sum())*100


cardio_df = cardio_df.round()

# Combining cycling and running data into one row for each

## Rename activity
cardio_df['activity'] = cardio_df['activity'].replace({'Cycling (Indoor)': 'Cycling',
                                                      'Running (Indoor)': 'Running'})

## Groupby and sum activity
cardio_df = cardio_df.groupby(['activity']).sum().reset_index()
cardio_df


fig = px.treemap(cardio_df, 
                 path=['activity'], 
                 values='%_of_total_time',
                 color='%_of_total_time', 
                 color_continuous_scale='Blues'
                )

fig.update_layout(template='ggplot2',
                  title="Total Time on Legs (by activity type)",
                  #treemapcolorway = ["blue"],
                 )
fig.update_traces(root_color="green",
                  marker=dict(cornerradius=5),
                  labels = ['Cycling', 'Running', 'Walking'],
                  values = list(cardio_df['%_of_total_time']),
                  textinfo = "label+value"
                 )

fig.update_layout(margin = dict(t=50, l=25, r=25, b=25))
fig.show()


fig = go.Figure()

# add the blood_glucose line trace to the plot
fig.add_trace(
    go.Scatter(x=glucose.index, 
               y=glucose['blood_glucose(mg/dl)'].rolling(7, 1).mean(), # 7-day moving average
               mode='lines', 
               name='Average blood glucose', 
               yaxis="y1",  # first y-axis

               )
)

# add the distance line trace to the plot
fig.add_trace(
    go.Scatter(x=run.index, 
               y=run['distance(km)'].rolling(7, 1).mean(), # 7-day moving average
               mode='lines', 
               name='Total weekly distance',
               yaxis="y2",  # second y-axis
               )
)

# Before and After RS
fig.add_shape(type='line', x0='2023-01-21', y0=0, x1='2023-01-21', y1=max(glucose['blood_glucose(mg/dl)'])-10,
              line=dict(color='black', width=3, dash='dash'))
# Annotating the RS
fig.add_annotation(x='2023-01-21', y=max(glucose['blood_glucose(mg/dl)']), 
                   text='Start of Running School', 
                   showarrow=True, arrowhead=1
                  )


# show both y-axes in their own y-scale
fig.update_layout(
    template='ggplot2',
    title='Blood glucose vs Running Distance',
    xaxis_title='Week', 
    yaxis=dict(
        title='blood_glucose(mg/dl)',
        #titlefont=dict(color='blue'),
        #tickfont=dict(color='blue')
    ),
    yaxis2=dict(
        title='distance(km)',
        #titlefont=dict(color='red'),
        #tickfont=dict(color='red'),
        overlaying='y',
        side='right'
    )
)

# show the plot
fig.show()

	insulin_delivery(iu)	purpose
date
2023-03-04	35.0	Bolus
2023-03-04	10.0	Basal
2023-03-05	23.0	Bolus
2023-03-05	10.0	Basal
2023-03-06	3.0	Bolus

	active_energy_burned(kcal)	activity	distance(km)	duration(s)	elevation:_ascended(m)	elevation:_maximum(m)	elevation:_minimum(m)	heart_rate_zone:_a_easy_(<115bpm)(%)	heart_rate_zone:_b_fat_burn_(115-135bpm)(%)	heart_rate_zone:_c_moderate_training_(135-155bpm)(%)	heart_rate_zone:_d_hard_training_(155-175bpm)(%)	heart_rate_zone:_e_extreme_training_(>175bpm)(%)	heart_rate:_average(count/min)	heart_rate:_maximum(count/min)	mets_average(kcal/hr·kg)	weather:_humidity(%)	weather:_temperature(degc)
date
2023-03-21	59.407	Yoga	NaN	748.569	NaN	NaN	NaN	0.937	0.063	0.000	0.0	0.0	97.928	125.0	4.444	77.0	12.77
2023-03-22	51.217	Walking	0.780	586.305	25.27	72.211	45.940	1.000	0.000	0.000	0.0	0.0	84.696	97.0	5.921	82.0	8.66
2023-03-22	295.996	Traditional Strength Training	NaN	4177.796	NaN	NaN	NaN	0.873	0.073	0.054	0.0	0.0	94.049	151.0	2.260	82.0	8.58
2023-03-22	114.325	Walking	2.316	1666.656	25.04	71.709	45.807	0.998	0.002	0.000	0.0	0.0	74.951	116.0	3.622	81.0	9.11
2023-03-22	64.154	Walking	1.047	907.100	17.43	60.478	49.434	0.983	0.017	0.000	0.0	0.0	84.243	118.0	4.949	78.0	12.18

	active_energy_burned(kcal)	basal_energy_burned(kcal)	carbohydrates(g)	fat_saturated(g)	fat_total(g)	protein(g)	step_count(count)
date
2023-03-18	1039.153	1544.700	578.0	9.267	38.0	106.0	7204.112
2023-03-19	1109.846	1541.463	551.0	8.101	35.0	101.0	14835.518
2023-03-20	973.931	1541.861	504.0	5.421	29.0	121.0	12956.085
2023-03-21	1140.518	1541.979	502.0	7.199	39.0	104.0	14477.000
2023-03-22	609.878	1013.088	433.0	8.930	32.0	108.0	7680.007

	blood_glucose(mg/dl)	insulin_delivery(iu)
date
2023-03-22	124.0	NaN
2023-03-22	123.0	NaN
2023-03-22	125.0	NaN
2023-03-22	125.0	NaN
2023-03-22	125.0	NaN

	blood_glucose(mg/dl)	insulin_delivery(iu)
date
2023-03-18	138.562500	0.0
2023-03-19	140.038194	0.0
2023-03-20	157.086806	0.0
2023-03-21	135.003472	0.0
2023-03-22	152.090323	0.0

ANALYSIS OF MY RUNNING WORKOUTS¶

GATHERING THE DATA¶

ASSESSING THE DATA¶

CLEANING THE DATA¶

1) Aggregate daily data from CGM ✅¶

2) Convert 'duration' to minutes ✅¶

3) Create 'running' dataframe¶

4) Renaming target columns¶

5) Aggregate data for workouts in same day¶

VISUALISING THE DATA¶

BACK AT IT - Recovery Progression: Workout's distance, calories and duration¶

HEART RATE ZONES ANALYSIS¶

WALKING MY WAY BACK¶

RUNNING AND BLOOD GLUCOSE¶

BACK AT IT - Recovery Progression: Workout's distance, calories and duration¶

Starting slow again¶

Gaining Momentum: "Running School" Program¶

HEART RATE ZONES ANALYSIS¶

Extra: Average HR before and during the Running School.¶

WALKING MY WAY BACK¶

Walking is the most important!¶

Analysis process¶

I have learned my lesson¶

RUNNING AND BLOOD GLUCOSE¶

See you in the next dashboard! 🌱🍌💪🏻🏃🏻‍♂️¶

	active_energy_burned(kcal)	activity	distance(km)	duration(m)	elevation:_ascended(m)	elevation:_maximum(m)	elevation:_minimum(m)	heart_rate_zone:_a_easy_(<115bpm)(%)	heart_rate_zone:_b_fat_burn_(115-135bpm)(%)	heart_rate_zone:_c_moderate_training_(135-155bpm)(%)	heart_rate_zone:_d_hard_training_(155-175bpm)(%)	heart_rate_zone:_e_extreme_training_(>175bpm)(%)	heart_rate:_average(count/min)	heart_rate:_maximum(count/min)	mets_average(kcal/hr·kg)	weather:_humidity(%)	weather:_temperature(degc)
date
2023-03-10	515.472	Running	9.104	61.980817	45.27	84.313	45.149	0.017	0.111	0.659	0.213	0.0	146.439	163.0	8.710	87.0	8.07
2023-03-14	177.655	Running	3.085	23.411883	38.89	132.882	46.554	0.322	0.341	0.337	0.000	0.0	122.366	144.0	8.031	89.0	9.53
2023-03-14	219.222	Running	4.182	33.298567	4.99	88.997	44.477	0.305	0.413	0.282	0.000	0.0	123.195	146.0	7.114	91.0	9.09
2023-03-17	587.974	Running	8.818	60.425883	75.97	92.401	45.330	0.010	0.284	0.706	0.000	0.0	139.452	153.0	10.044	68.0	8.41
2023-03-21	534.337	Running	9.070	60.309700	51.23	96.909	45.033	0.000	0.054	0.401	0.545	0.0	156.176	173.0	9.190	84.0	8.66

	kcal_burned	distance(km)	duration(m)	zone1_(<115bpm)(%)	zone2_(115-135bpm)(%)	zone3_(135-155bpm)(%)	zone4_(155-175bpm)(%)	zone5_(>175bpm)(%)	avg_HR	max_HR
date
2023-03-03	604.088	8.329	60.453483	0.0160	0.270	0.7140	0.000	0.0	137.3540	152.0
2023-03-10	515.472	9.104	61.980817	0.0170	0.111	0.6590	0.213	0.0	146.4390	163.0
2023-03-14	396.877	7.267	56.710450	0.3135	0.377	0.3095	0.000	0.0	122.7805	145.0
2023-03-17	587.974	8.818	60.425883	0.0100	0.284	0.7060	0.000	0.0	139.4520	153.0
2023-03-21	534.337	9.070	60.309700	0.0000	0.054	0.4010	0.545	0.0	156.1760	173.0

	kcal_burned	distance(km)	duration(m)	zone1_(<115bpm)(%)	zone2_(115-135bpm)(%)	zone3_(135-155bpm)(%)	zone4_(155-175bpm)(%)	zone5_(>175bpm)(%)	avg_HR	max_HR
date
2022-11-04	36.571	0.668	4.154350	0.041	0.184	0.775	0.0	0.0	139.163	150.0
2022-11-19	35.645	0.669	4.632467	0.500	0.500	0.000	0.0	0.0	120.250	133.0
2022-11-22	40.238	0.669	4.396233	0.000	0.510	0.490	0.0	0.0	136.157	146.0
2022-12-05	38.641	0.657	4.295183	0.020	0.451	0.529	0.0	0.0	135.353	143.0
2022-12-06	37.179	0.641	3.996717	0.044	0.222	0.734	0.0	0.0	136.867	147.0

	HR_Zone	avg_time_in_zone	avg_time_in_zone(%)
0	zone1_(<115bpm)(%)	0.227636	22
1	zone2_(115-135bpm)(%)	0.415977	41
2	zone3_(135-155bpm)(%)	0.316477	31
3	zone4_(155-175bpm)(%)	0.039909	3

	activity	active_energy_burned(kcal)	duration(m)	%_of_total_time
0	Cycling	21878.0	2510.0	20.0
1	Running	11643.0	1473.0	12.0
2	Walking	34127.0	8554.0	68.0